Scholarlink

Extreme weather events have a tremendous influence on global and national economy, affecting food harvests, human lives, and ecosystems. The current research uses a novel method to forecast severe weather by combining supervised machine learning algorithms with time series modeling. The study analyses the accuracy of proven methods, inclusive of ARIMA, SVR, RFR, and LSTM Networks, using a real-world dataset of daily stock prices as a case study. The results suggest that the LSTM algorithm is best in stock price forecasting, with SVR, RFR, and ARIMA exhibiting respectable accuracy. This research centered on the potential of machine learning to improve weather forecasts, which will have an impact on industries such as agriculture, transportation, and energy. It emphasizes the importance of high-quality data and accurate variable characterization for best model accuracy, and it anticipates continuous advances in weather forecasting as data sources and forecasting systems change.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Enhancing Time Series Forecasting with Machine Learning and Deep Learning Models

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Amit Kumar Sharma,
  • Ritwick Roy,
  • Sandeep Chaurasia

摘要

Extreme weather events have a tremendous influence on global and national economy, affecting food harvests, human lives, and ecosystems. The current research uses a novel method to forecast severe weather by combining supervised machine learning algorithms with time series modeling. The study analyses the accuracy of proven methods, inclusive of ARIMA, SVR, RFR, and LSTM Networks, using a real-world dataset of daily stock prices as a case study. The results suggest that the LSTM algorithm is best in stock price forecasting, with SVR, RFR, and ARIMA exhibiting respectable accuracy. This research centered on the potential of machine learning to improve weather forecasts, which will have an impact on industries such as agriculture, transportation, and energy. It emphasizes the importance of high-quality data and accurate variable characterization for best model accuracy, and it anticipates continuous advances in weather forecasting as data sources and forecasting systems change.